© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48856
    Prev
    Next
    INDEX
    Explanations

    Foreign numbered lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     নিব
    -0.08
    agic
    -0.07
    illiance
    -0.07
    isummaa
    -0.07
     Solo
    -0.07
     stå
    -0.07
    руул
    -0.07
    abelle
    -0.07
     always
    -0.07
    ത്തിക
    -0.07
    POSITIVE LOGITS
    zele
    0.10
    τηγ
    0.09
    mdl
    0.09
    ijding
    0.09
    ענג
    0.08
    znych
    0.08
    za
    0.08
    ого
    0.08
    zan
    0.08
    יטל
    0.08
    Activations Density 0.005%

    No Known Activations